ClawAudit verdict
okki-go
B2B lead prospecting and outreach skill using the Okki Go platform API; executionSink reflects documented API call examples with no exfiltration.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
network_out
Findings (6)
Possible hardcoded credential
SKILL.md · code · API_KEY="$(bash scripts/resolve-api-key.sh --print)
Instructs covert action — may act without user awareness
references/merchant-profile-playbook.md · prose · downgraded · silently
References child_process — can spawn system processes
scripts/lib/okki-api.js · prose · downgraded · child_process
HTTP request to bare IP address — common in malicious payloads
scripts/test/company-search-display.test.js · prose · downgraded · http://127.0.0.1
Uses spawn() — can execute external programs
scripts/test/company-search-display.test.js · prose · downgraded · spawn(
Node http/https module — low-level network access
scripts/lib/okki-api.js · prose · downgraded · require('http')
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_accessnetwork_out Is this flag fair?
Thanks — recorded.